Article Per Year (5 Year)
p-Index From 2021 - 2026
4.359
P-Index
This Author published in this journals
All Journal International Journal of Advances in Applied Sciences PROtek : Jurnal Ilmiah Teknik Elektro Ainet : Jurnal Informatika Indonesian Journal of Data and Science Jurnal Teknik Informatika (JUTIF) Jurnal Algoritma, Logika dan Komputasi Jurnal Informatika Progres Mechatronics Journal in Professional and Entrepreneur (MAPLE) ARUS JURNAL SAINS DAN TEKNOLOGI Journal of Muhammadiyah’s Application Technology
Muhyiddin A.M Hayat
Informatika, Universitas Muhammadiyah Makassar
Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Materials Science & Nanotechnology Mathematics Physics Social Sciences Other

Published : 34 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 34 Documents
Search

 1   2   3   4 
Peningkatan Akurasi Prediksi Kebutuhan Obat BPJS PRB melalui Integrasi Analisis Diferensial dan Deep Learning Hermanto, Chalidah Azzahrah; Rachman, Fachrim Irhamna; A.M Hayat, Muhyiddin; H, chalidah_azzahra00
Journal of Muhammadiyah’s Application Technology Vol. 4 No. 3 (2025)
Publisher : Universitas Muhammadiyah Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26618/k6t40472

Abstract

ABSTRAKProgram Rujuk Balik (PRB) BPJS Kesehatan bertujuan menjamin keberlanjutan pengobatan pasien penyakit kronis. Namun, fluktuasi kebutuhan obat sering menimbulkan permasalahan overstock dan stockout di apotek mitra BPJS. Penelitian ini bertujuan mengintegrasikan analisis diferensial dan algoritma deep learning Long Short-Term Memory (LSTM) untuk meningkatkan akurasi prediksi kebutuhan obat PRB. Data yang digunakan berupa transaksi penjualan obat pasien BPJS PRB di Apotek Kimia Farma Cendrawasih periode Januari 2022 hingga Juli 2024. Analisis diferensial digunakan untuk menghitung perubahan tingkat pertama (delta 1) dan tingkat kedua (delta 2) penjualan, yang selanjutnya dijadikan fitur tambahan pada model LSTM. Evaluasi model dilakukan menggunakan metrik Mean Squared Error (MSE), Mean Absolute Error (MAE), dan Mean Absolute Percentage Error (MAPE). Hasil penelitian menunjukkan bahwa integrasi analisis diferensial dengan LSTM mampu meningkatkan akurasi prediksi, dengan model terbaik menghasilkan nilai MAE rata-rata di bawah 20 untuk sebagian besar produk. Temuan ini berimplikasi pada peningkatan efektivitas perencanaan dan pengadaan obat PRB berbasis data historis dan tren perubahan.Kata Kunci: Prediksi Obat, BPJS PRB, LSTM, Deep Learning, Analisis Diferensial ABSTRACTThe BPJS Kesehatan Rujuk Balik Program (PRB) aims to ensure the continuity of treatment for patients with chronic diseases. However, fluctuations in medicine demand frequently cause overstock and stockout problems at BPJS partner pharmacies. This study aims to integrate differential analysis and the Long Short-Term Memory (LSTM) deep learning algorithm to improve the accuracy of PRB medicine demand forecasting. The data used consist of transaction records of PRB patient medicine sales at Kimia Farma Cendrawasih Pharmacy from January 2022 to July 2024. Differential analysis was applied to calculate the first-order change (delta 1) and second-order change (delta 2) in sales, which were subsequently incorporated as additional features in the LSTM model. Model performance was evaluated using Mean Squared Error (MSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE). The results indicate that integrating differential analysis with LSTM improves prediction accuracy, with the best-performing model achieving average MAE values below 20 for most products. These findings have important implications for enhancing data-driven planning and procurement of PRB medicines based on historical trends and demand dynamics.Keyworsds: Medicine Forecasting, BPJS PRB, LSTM, Deep Learning, Differential Analysis
Penerapan Watermark‎‎‎‎‎ Tak Terlihat pada Materi Pembelajaran ‎Digital Menggunakan QR Code‎ dan Least Significant Bit Wahyuni, Titin; Hayat, Muhyiddin AM; khairat, arikal
Journal of Muhammadiyah’s Application Technology Vol. 4 No. 3 (2025)
Publisher : Universitas Muhammadiyah Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26618/hqt4ec35

Abstract

ABSTRAKPerkembangan bahan ajar digital meningkatkan risiko pelanggaran hak cipta dan pemalsuan konten, sehingga diperlukan mekanisme perlindungan yang tidak mengganggu tampilan visual. Penelitian ini mengimplementasikan watermark‎ing‎ tak terlihat dengan menggabungkan Quick Response (QR) Code sebagai pembawa informasi dan steganografi‎ Least Significant Bit (LSB) sebagai teknik penyisipan pada citra yang terdapat dalam dokumen. Sistem dikembangkan berbasis web dengan tiga modul utama: pembuatan QR Code‎, penyisipan watermark‎, dan validasi dokumen. Evaluasi dilakukan pada 10 dokumen berformat DOCX dan PDF dengan total 169 gambar. Kinerja imperceptibility diukur menggunakan Peak Signal-to-Noise Ratio (PSNR) dan Mean Squared Error (MSE). Hasil pengujian menunjukkan PSNR berada pada rentang 55,4–67,1 dB dengan MSE sangat rendah (0,02–0,19), menandakan kualitas visual citra tetap terjaga. Selain itu, seluruh watermark‎ berhasil diekstraksi (100%) dan QR Code‎ dapat dipindai tanpa kegagalan. Validasi integritas payload‎ secara opsional menggunakan CRC32 terbukti membantu memastikan keutuhan data yang disisipkan. Temuan ini menunjukkan bahwa kombinasi QR Code‎ dan LSB efektif, andal, dan efisien untuk melindungi bahan ajar digital dari penyalahgunaan tanpa menurunkan kualitas visual.Kata Kunci: Watermark‎ing‎ tak terlihat; QR Code‎; steganografi‎; Least Significant Bit; bahan ajar digital. ABSTRACTThe growth of digital teaching materials increases the risk of copyright infringement and content tampering, requiring protection mechanisms that do not degrade visual quality. This study implements an invisible watermark‎ing‎ scheme by combining Quick Response (QR) Code as the information carrier and Least Significant Bit (LSB) steganography for embedding within images contained in documents. A web-based system was developed with three core modules: QR Code‎ generation, watermark‎ embedding, and document validation. The evaluation used 10 DOCX and PDF documents comprising 169 images. Imperceptibility was assessed using Peak Signal-to-Noise Ratio (PSNR) and Mean Squared Error (MSE). Experimental results indicate PSNR values of 55.4–67.1 dB with very low MSE (0.02–0.19), confirming that visual quality is preserved. All embedded watermark‎s were successfully extracted (100%), and the QR Code‎s remained fully scannable without failure. Optional payload‎ integrity checking using CRC32 further ensured the correctness of embedded data. Overall, the proposed QR Code‎–LSB combination provides a reliable and efficient approach to protect digital teaching materials against misuse while maintaining visual fidelity.Keywords: Invisible watermark‎ing‎; QR Code‎; steganography; Least Significant Bit; digital teaching materials.
Penerapan Natural Language Processing dan Regular Expressions dalam Validasi Artikel Ilmiah Azzahra, Fatimah; Anggraeni , Desi; AM Hayat , Muhyiddin
Journal of Muhammadiyah’s Application Technology Vol. 4 No. 3 (2025)
Publisher : Universitas Muhammadiyah Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26618/dkjw7933

Abstract

ABSTRAKPenelitian ini membahas penerapan Natural Language Processing (NLP) dalam proses validasi otomatis aturan penulisan artikel ilmiah pada AINET: Jurnal Informatika. Sistem dikembangkan dalam bentuk aplikasi web interaktif yang bertujuan untuk memeriksa kesesuaian struktur dan format artikel ilmiah secara otomatis, meliputi penulisan judul, identitas penulis, abstrak, kata kunci, bagian wajib artikel, serta format referensi yang digunakan. Metode yang diterapkan dalam penelitian ini adalah pendekatan rule-based, yang terdiri dari beberapa tahapan, yaitu ekstraksi teks dari dokumen, preprocessing NLP, segmentasi dokumen, serta pencocokan pola teks menggunakan Regular Expressions (Regex). Evaluasi sistem dilakukan menggunakan metode black-box testing terhadap 20 artikel jurnal sebagai data uji untuk mengukur tingkat ketepatan hasil validasi yang dihasilkan sistem. Hasil pengujian menunjukkan bahwa sistem mampu mencapai tingkat akurasi sebesar 90%, di mana 18 artikel berhasil divalidasi sesuai dengan kondisi sebenarnya. Temuan ini menunjukkan bahwa integrasi NLP dan Regex efektif dalam mendukung proses validasi penulisan artikel ilmiah secara efisien, cepat, dan konsisten. Namun demikian, sistem masih memiliki keterbatasan dalam mendeteksi abstrak bilingual, konsistensi penggunaan bahasa pada header, serta variasi format referensi, sehingga diperlukan pengembangan lanjutan untuk meningkatkan keandalan dan fleksibilitas sistem.Kata Kunci: Natural Language Processing, Regular Expressions, Validasi Penulisan, Artikel Ilmiah, AINET: Jurnal InformatikaABSTRACTThis study discusses the application of Natural Language Processing (NLP) in the automatic validation of scientific article writing rules in AINET: Journal of Informatics. The system was developed as an interactive web-based application aimed at automatically checking the conformity of article structure and formatting, including the title, author information, abstract, keywords, mandatory article sections, and references. The method used in this study is a rule-based approach, which consists of several stages, namely text extraction, NLP preprocessing, document segmentation, and pattern matching using Regular Expressions (Regex). System evaluation was conducted using the black-box testing method on 20 journal articles to measure the accuracy of the validation results. The testing results show that the system achieved an accuracy rate of 90%, with 18 articles successfully validated in accordance with actual conditions. These findings indicate that the integration of NLP and Regex is effective in supporting the validation process of scientific article writing in an efficient, fast, and consistent manner. However, the system still has limitations in detecting bilingual abstracts, language consistency in headers, and variations in reference formats, indicating the need for further development to improve system reliability and flexibility.Keyworsds: Natural Language Processing, Regular Expressions, Writing Validation, Scientific   Articles, AINET: Journal of Informatics
Fine-Tuning a Large Language Model on Vertex AI for a New Student Registration Chatbot at Universitas Muhammadiyah Makassar Desi Anggreani; Muhyiddin A M Hayat; Lukman; Faisal, Ahmad; Khadijah; Darniati
Indonesian Journal of Data and Science Vol. 7 No. 1 (2026): Indonesian Journal of Data and Science
Publisher : yocto brain

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56705/ijodas.v7i1.341

Abstract

This study addresses the limitations of manual admission services at Universitas Muhammadiyah Makassar, which often result in delayed and inconsistent information delivery. To overcome these challenges, an institution-specific chatbot was developed by fine-tuning the Gemini 2.5 Flash model on the Google Cloud Vertex AI platform. The model was trained using a curated domain-specific dataset of 1,430 question–answer pairs derived from official documents and frequently asked questions. The fine-tuning process employed supervised learning to enhance contextual relevance and response accuracy. System performance was evaluated using automated text quality metrics, achieving an average BLEU score of 0.23526 and a ROUGE-L Recall score of 0.53424, indicating satisfactory lexical and semantic similarity. Furthermore, a user acceptance evaluation involving 52 respondents yielded a Customer Satisfaction Score (CSAT) of 84.2%, reflecting high user satisfaction. These results demonstrate that fine-tuning a Large Language Model (LLM) for specific institutional needs effectively improves both response quality and service reliability. Ultimately, this approach offers a practical and scalable solution for modernizing student admission services in higher education, ensuring that prospective students receive accurate information in a timely and efficient manner.
Co-Authors . Darniati Abd Rahman, Aedah Abrah, Rezkytullah Ahmad Faisal Akbar DB, Andi Muhammad Akbar, Syahril Anggraeni , Desi Anggreani, Desi Bakti, Rizki Yusliana Basyar, Muhammad Yusuf Danuputri, Chyquitha Danuputri, Chyquitha Dedi Setiawan Desi Anggreani Djalil, Sony Achmad Dzakki Adam, Ahmad Wildan Fachrim Irhamna Rachman Faeruddin, Muhammad Asygar Fahrim Irhmna Rachman Fatimah Azzahra H, chalidah_azzahra00 Hadawina Hadawina Haidul, Haidul Hermanto, Chalidah Azzahrah Khadijah khairat, arikal Lukman LUKMAN ANAS Lukman Lukman Lukman Lukman Muh Nur Aqsal Aminullah Muhammad Faisal Mujidah, Jihan Izzathul Nisha, Khairun Nur Alam Nur, Muhammad Ikhsan Rahman, Fahrim Irhamna RAHMANIA Rahmania RAMLI, ANDI RAODATUL ADAWIYAH Rasyidi, Muhammad Fachri Reski Abbas Ridwang Ridwang Ridwang Ridwang Ridwang, Ridwang Risal S. Kuba, Muhammad Syafa'at Salsabila, Ismi Sarina Sunarti Suriani Suriani Syamsuri, Andi Makbul Syarifuddin, Nur Annisa Titin Wahyuni Usman, Ansharullah Patiroi Utama, Prengki Putra Wahid, Abd Rahman